© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50592
    Prev
    Next
    INDEX
    Explanations

    court of appeals publication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aria
    -0.08
    able
    -0.07
    çļĦ人çĶŁ
    -0.07
    a
    -0.06
     Gara
    -0.06
     Carvalho
    -0.06
    aian
    -0.06
    妥妥
    -0.06
    castle
    -0.06
    éder
    -0.05
    POSITIVE LOGITS
    çļĦåĬĽéĩı
    0.09
    olen
    0.08
    æŃ£æľ¬
    0.08
    odo
    0.08
    ÏĦÏī
    0.08
    æij¸æij¸
    0.08
    汹汹
    0.08
    ìĿĺ
    0.08
    çļĦè¯Ŀé¢ĺ
    0.08
    çļĦä¸ľè¥¿
    0.07
    Activations Density 0.247%

    No Known Activations